INDEX
    Explanations

    words related to feelings and emotional states

    New Auto-Interp
    Negative Logits
    anning
    -0.15
    oi
    -0.15
    é
    -0.14
    ---</
    -0.14
    orse
    -0.14
    antar
    -0.14
    ÃĹ↵↵
    -0.14
    lookup
    -0.14
     Merr
    -0.13
    ited
    -0.13
    POSITIVE LOGITS
    asher
    0.17
    velt
    0.16
    atak
    0.15
    atur
    0.15
    à¥įवत
    0.14
    tron
    0.14
    mere
    0.14
    uteur
    0.14
    yntax
    0.14
    utz
    0.14
    Act Density 0.015%

    No Known Activations